{"title":"Strain-level typing of Wickerhamomyces anomalus using Fourier transform infrared spectroscopy and whole-genome sequencing","authors":"Asuka Kashiwaba , Asako Mitani , Takumi Sonoda , Naofumi Shigemune , Hiroki Takahashi","doi":"10.1016/j.mimet.2025.107184","DOIUrl":"10.1016/j.mimet.2025.107184","url":null,"abstract":"<div><div>In industrial settings, identifying the source of microbial contamination is crucial for effective microbiological risk assessment. While various strain identification technologies exist, many struggle with practicality, accuracy, and reproducibility. Fourier Transform Infrared Spectroscopy (FT-IR) has emerged as a rapid method, demonstrating a strong correlation with whole-genome sequencing (WGS) for certain bacteria. However, its accuracy for identifying yeast strains has been limited.</div><div>This study focuses on improving the accuracy of FT-IR for yeast strain identification by optimizing pretreatment conditions. We conducted phylogenetic analyses on <em>Wickerhamomyces anomalus</em> using both WGS single-nucleotide polymorphisms (SNPs) and FT-IR. Although initial FT-IR results were less accurate than WGS, refining the culture and sample preparation conditions led to significant improvements. We tested 16 different conditions, using Euclidean Distances (EDs) and dendrogram comparisons to evaluate discrimination ability, including metrics like the F-measure and adjusted Rand index (ARI).</div><div>The most accurate and reproducible FT-IR results were achieved with incubation in Sabouraud dextrose (SD) broth aligning closely with WGS results. This optimized FT-IR protocol now allows for rapid and precise strain-level discrimination of <em>W. anomalus</em>, offering a practical tool for tracking contamination sources in industrial environments.</div></div>","PeriodicalId":16409,"journal":{"name":"Journal of microbiological methods","volume":"236 ","pages":"Article 107184"},"PeriodicalIF":1.7,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144505999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Steven David , Dayana Salazar , Paula Puente Cantillo, Alvaro Barrera-Ocampo
{"title":"Streamlined E. coli expression and purification of amyloid beta peptides via inclusion body formation and fluorescence monitoring","authors":"Steven David , Dayana Salazar , Paula Puente Cantillo, Alvaro Barrera-Ocampo","doi":"10.1016/j.mimet.2025.107182","DOIUrl":"10.1016/j.mimet.2025.107182","url":null,"abstract":"<div><div>The recombinant production of amyloid beta peptides poses significant challenges due to their high aggregation propensity and cytotoxicity in bacterial hosts. In this study, we present a streamlined and reproducible method for the expression and purification of methionine-modified Aβ40 and Aβ42 peptides in <em>Escherichia coli</em> BL21 (DE3) pLysS. By leveraging inclusion body formation, the protocol enhances yield while simplifying purification. A key feature of this approach is the incorporation of real-time fluorescence spectroscopy and microscopy using Thioflavin-S and propidium iodide, enabling non-invasive monitoring of IB formation and expression dynamics. Purification was achieved through pH modulation, anion exchange chromatography, and ultrafiltration, yielding average peptide concentrations of 3.2 ± 1.3 mg/L for Aβ40 and 4.8 ± 3.2 mg/L for Aβ42. High-performance liquid chromatography confirmed average purities of 90.2 % ± 0.8 % for Aβ40 and 84.0 % ± 17.4 % for Aβ42. The structural integrity, aggregation kinetics, and neurotoxicity of the peptides were validated by PICUP, Thioflavin-T fluorescence assays, and cytotoxicity tests in primary hippocampal neurons. This tag-free, cost-effective platform provides a scalable solution for producing biologically active amyloid beta peptides, facilitating their use in structural biology, neurodegenerative disease research, and high-throughput drug screening.</div></div>","PeriodicalId":16409,"journal":{"name":"Journal of microbiological methods","volume":"236 ","pages":"Article 107182"},"PeriodicalIF":1.7,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144506000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kyoka Aiki, Rin Tsuchiya, Aiho Kushida, Tatsuya Tominaga
{"title":"Rapid counting of Kazachstania humilis and Saccharomyces cerevisiae in sourdough by deep learning-based classifier","authors":"Kyoka Aiki, Rin Tsuchiya, Aiho Kushida, Tatsuya Tominaga","doi":"10.1016/j.mimet.2025.107183","DOIUrl":"10.1016/j.mimet.2025.107183","url":null,"abstract":"<div><div>When maintaining sourdough through backslopping, bakers must ensure that the yeast mycobiota remains stable. By introducing two-staged incubation temperatures for cultivation, we found that the colonies of <em>Kazachstania humilis</em> and <em>Saccharomyces cerevisiae</em> could be differentiated by size and color. We then developed a classifier that used the deep-learning method, YOLO, to automatically count these colonies. For sourdough isolates of <em>K. humilis</em> and <em>S. cerevisiae</em>, the classifier had accuracies of 0.99 and 0.98, respectively. This classifier also showed accuracies greater than 0.95 for <em>S. cerevisiae</em> strains used in bread, sake, and wine. To investigate the practical feasibility, the sourdough was repeatedly refreshed by backslopping at 25 °C, 30 °C, and 35 °C, with the goal of artificially fluctuating the yeast mycobiota. At 25 °C, <em>K. humilis</em> and <em>S. cerevisiae</em> accounted for proportions of approximately 25 % and 75 %, respectively, whereas at 30 °C and 35 °C, <em>K. humilis</em> comprised less than 1 % of the mycobiota. The accuracy of this classifier was 0.98 for <em>K. humilis</em> and 0.99 for <em>S. cerevisiae</em>; this was very close to the accuracy obtained with manual counting, indicating that the classifier could detect changes in the yeast mycobiota. The classifier took approximately 126 milliseconds to count colonies on one Petri dish. The use of our novel classifier can enable fast, less-laborious, and objective judgement, potentially facilitating the ability of small-scale artisan bakeries to manage fermentation on a daily basis.</div></div>","PeriodicalId":16409,"journal":{"name":"Journal of microbiological methods","volume":"236 ","pages":"Article 107183"},"PeriodicalIF":1.7,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144491289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tariq Aziz , Muhammad Aqib Shabbir , Abid Sarwar , Ayaz Ali Khan , Liqing Zhao , Zhennai Yang , Ashwag Shami , Maher S. Alwethaynani , Fahad Al-Asmari , Abeer M. Alghamdi , Fakhria A. Al-Joufi
{"title":"Exploring the multifaceted probiotic potential of Lactiplantibacillus plantarum NMGL2, investigating its antimicrobial resistance profiles and bacteriocin production","authors":"Tariq Aziz , Muhammad Aqib Shabbir , Abid Sarwar , Ayaz Ali Khan , Liqing Zhao , Zhennai Yang , Ashwag Shami , Maher S. Alwethaynani , Fahad Al-Asmari , Abeer M. Alghamdi , Fakhria A. Al-Joufi","doi":"10.1016/j.mimet.2025.107178","DOIUrl":"10.1016/j.mimet.2025.107178","url":null,"abstract":"<div><h3>Background</h3><div><em>Lactiplantibacillus plantarum</em> is widely recognized for its probiotic and antimicrobial properties, making it a valuable candidate for food and clinical applications. Genomic characterization provides deeper insight into its potential health benefits and safety profile.</div></div><div><h3>Aim</h3><div>This study aimed to sequence and analyze the genome of <em>L. plantarum</em> NMGL2 to evaluate its antimicrobial resistance, probiotic potential, and genetic suitability for biotechnological applications.</div></div><div><h3>Methods</h3><div>The genomic DNA of L. <em>plantarum</em> NMGL2 was extracted and sequenced using Illumina technology. Genome assembly and annotation were performed, followed by gene prediction using Prokka and identification of antimicrobial resistance genes, virulence factors, and probiotic markers via BLAST. Metagenomic analysis of gut microbiota samples and phylogenetic analysis were conducted to assess strain relationships with other L. <em>plantarum</em> isolates.</div></div><div><h3>Results</h3><div>The genome analysis revealed approximately 3000 protein-coding genes, including those encoding bile salt hydrolase, antimicrobial peptides, and antibiotic resistance determinants. Phylogenetic analysis showed that NMGL2 is closely related to other probiotic L. <em>plantarum</em> strains, supporting its probiotic characteristics and its potential role in combating pathogens.</div></div><div><h3>Conclusion</h3><div><em>L. plantarum</em> NMGL2 demonstrates promising probiotic traits and carries genes that support its application in food safety and clinical contexts. Further, in vivo studies are needed to validate its health benefits and ensure safety, particularly in treating gastrointestinal disorders.</div></div>","PeriodicalId":16409,"journal":{"name":"Journal of microbiological methods","volume":"236 ","pages":"Article 107178"},"PeriodicalIF":1.7,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiahong Han , Yao Zang , Haojie Zhu, Yingjie Feng, Yitian Zang, Huaping Zheng, Tao Zha, Xinyi Yin, Juncheng Luo, Changming Wang, Jiarong Hu
{"title":"Combination of slightly electrolyzed water and ultraviolet light for the treatment of Staphylococcus aureus-induced skin abscesses in mice by effective inactivation of Staphylococcus aureus","authors":"Jiahong Han , Yao Zang , Haojie Zhu, Yingjie Feng, Yitian Zang, Huaping Zheng, Tao Zha, Xinyi Yin, Juncheng Luo, Changming Wang, Jiarong Hu","doi":"10.1016/j.mimet.2025.107181","DOIUrl":"10.1016/j.mimet.2025.107181","url":null,"abstract":"<div><div>In this study, the combined effectiveness of slightly acidic electrolyzed water (SAEW) and ultraviolet light-C (UV) (SAEW + UV) against infections caused by <em>Staphylococcus aureus</em> (<em>S. aureus</em>) was evaluated, both in vivo and in vitro, with a specific focus on skin abscess in mice. The superior effectiveness of the SAEW + UV combination compared to individual treatments with SAEW or UV alone was observed (<em>P</em> < 0.05). Notably, a significant nonlinear increase in <em>S. aureus</em> inactivation over time and effective chlorine concentrations was observed with the synergistic action of SAEW + UV (<em>P</em> < 0.05). Even in the presence of organic interference, remarkable efficacy in <em>S. aureus</em> eradication was demonstrated by SAEW + UV. Significantly, SAEW + UV efficiently removes <em>S. aureus</em> from mouse skin abscesses, leading to a reduction in bacterial load of visceral tissues, oxidative stress levels and inflammatory factors (<em>P</em> < 0.05). Consequently, facilitated regression of abscesses and accelerated wound healing in mice were observed. Notably, after 9 days of SAEW + UV treatment, 93.97 % wound healing rate was observed in mice, compared to the untreated model group with only 48.66 % healing achieved. These findings underscore the promising potential of SAEW + UV therapy in mitigating oxidative stress and expediting skin wound healing, owing to its effective bactericidal activity. However, to comprehensively elucidate the specific cellular signaling mechanisms involved in reducing oxidative stress, further research is imperative. In conclusion, SAEW + UV emerges as a highly promising therapeutic approach for treating skin diseases.</div></div>","PeriodicalId":16409,"journal":{"name":"Journal of microbiological methods","volume":"236 ","pages":"Article 107181"},"PeriodicalIF":1.7,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144365889","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xinggong Liang , Gongji Wang , Zhengyang Zhu , Wanqing Zhang , Yuqian Li , Jianliang Luo , Han Wang , Shuo Wu , Run Chen , Mingyan Deng , Hao Wu , Chen Shen , Gengwang Hu , Kai Zhang , Qinru Sun , Zhenyuan Wang
{"title":"Identification of bacterial infection types in decomposition stages at various temperatures using pathology images and artificial intelligence algorithms","authors":"Xinggong Liang , Gongji Wang , Zhengyang Zhu , Wanqing Zhang , Yuqian Li , Jianliang Luo , Han Wang , Shuo Wu , Run Chen , Mingyan Deng , Hao Wu , Chen Shen , Gengwang Hu , Kai Zhang , Qinru Sun , Zhenyuan Wang","doi":"10.1016/j.mimet.2025.107180","DOIUrl":"10.1016/j.mimet.2025.107180","url":null,"abstract":"<div><div>Bacterial infections present a significant threat to human health, and accurate identification of infection type is crucial for both clinical and forensic applications. Although traditional diagnostic methods are reliable, they are often time-consuming, require specialized personnel and equipment, and have limited accessibility. Previous studies have demonstrated that pathology images combined with artificial intelligence (AI) algorithms can effectively classify bacterial infections in fresh tissue samples. In this study, we extend this approach to identify bacterial infection types in decomposed tissue under varying temperature conditions. Our findings indicate that decomposition factors, such as putrefaction and autolysis, do not impair model performance. The model exhibits strong classification efficacy across all tested temperatures (25 °C, 37 °C, and 4 °C), demonstrating robustness and generalizability. The overall area under the curve (AUC) values exceeded 0.920 and 0.820 at the patch and whole slide image (WSI) levels, respectively, in the training and testing sets, while surpassing 0.990 at the patch-level in the external validation set. These results confirm that AI-driven computational pathology can reliably distinguish bacterial infection types, even in decomposition states. Our method offers a novel approach for bacterial diagnosis in forensic pathology and supports infection prevention during autopsies.</div></div>","PeriodicalId":16409,"journal":{"name":"Journal of microbiological methods","volume":"236 ","pages":"Article 107180"},"PeriodicalIF":1.7,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144298024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Rapid antibiotic sensitivity prediction in Pseudomonas aeruginosa using UV–vis-NIR spectroscopy and gray-box one-vs-all models","authors":"Tsung-Han Chou , Chi-Wei Chen , Su-Hua Huang , Ying-Tsong Chen , Yen-Wei Chu","doi":"10.1016/j.mimet.2025.107179","DOIUrl":"10.1016/j.mimet.2025.107179","url":null,"abstract":"<div><div><em>Pseudomonas aeruginosa</em> is a widespread pathogen known to cause infections in various hosts, particularly threatening immunocompromised patients. Although determining antibiotic sensitivity is crucial for appropriate patient care, existing diagnostic methods remain time-consuming, which can delay targeted therapy. In this study, we propose a novel, interpretable, and cost-effective framework that combines ultraviolet-visible-near-infrared (UV–Vis-NIR) spectroscopy with subgroup discovery and a one-vs-all multilayer perceptron (MLP) model to predict antibiotic sensitivity without the need for traditional culture methods. Unlike prior approaches that depend on expensive instruments or black-box algorithms, our method leverages spectral pattern interpretability to identify key wavelength features associated with distinct resistance categories. Testing on clinical isolates of <em>P. aeruginosa</em>, the model achieved optimal prediction accuracy within 10 min of culture time, significantly reducing the typical 48–72 h turnaround time of conventional culture-based susceptibility testing. This work demonstrates a promising direction for rapid, low-cost, and clinically actionable antimicrobial susceptibility testing that balances performance with explainability.</div></div>","PeriodicalId":16409,"journal":{"name":"Journal of microbiological methods","volume":"236 ","pages":"Article 107179"},"PeriodicalIF":1.7,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144302308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Peiyao Tan , Xuezheng Liang , Jing Yin , Ying Wang , Yanling Li , Xiaomin Yang , Bei Zhang , Hongping Zhang
{"title":"Molecular dynamics – Driven innovation in lateral flow immunoassay technology: Principles, methods, and applications","authors":"Peiyao Tan , Xuezheng Liang , Jing Yin , Ying Wang , Yanling Li , Xiaomin Yang , Bei Zhang , Hongping Zhang","doi":"10.1016/j.mimet.2025.107156","DOIUrl":"10.1016/j.mimet.2025.107156","url":null,"abstract":"<div><div>Lateral flow immunoassay (LFIA), a widely used point - of - care testing tool, holds significant value in disease diagnosis, food safety detection, and environmental monitoring. However, conventional LFIA faces limitations in sensitivity and specificity. This article delves into the application of molecular dynamics in LFIA technology, elaborating on the principles, methods, and applications of molecular dynamics - driven LFIA innovation. It first introduces the basic principles and simulation methods of molecular dynamics. Then, it conducts a detailed analysis of the key roles of molecular dynamics in optimizing LFIA technology, including the simulation of antigen - antibody interactions, optimization of labeling materials, and optimization of detection conditions. Finally, it explores the application prospects of molecular dynamics - driven LFIA technology in disease diagnosis, food safety detection, and environmental monitoring. This article aims to provide a theoretical basis and practical guidance for the further development of LFIA technology, promoting its application in more fields.</div></div>","PeriodicalId":16409,"journal":{"name":"Journal of microbiological methods","volume":"236 ","pages":"Article 107156"},"PeriodicalIF":1.7,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144234383","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vivian Heimbecker , Bárbara Pontarollo Dal Santos , Ana Paula Thomaz , Keite da Silva Nogueira , Camila Marconi
{"title":"Quantification of Lactobacillus spp. of interest for the study of the vaginal microbiota","authors":"Vivian Heimbecker , Bárbara Pontarollo Dal Santos , Ana Paula Thomaz , Keite da Silva Nogueira , Camila Marconi","doi":"10.1016/j.mimet.2025.107158","DOIUrl":"10.1016/j.mimet.2025.107158","url":null,"abstract":"<div><div>The optimal vaginal microbiota is dominated by <em>Lactobacillus</em> spp., particularly <em>Lactobacillus crispatus</em> or <em>Lactobacillus gasseri</em>. Lactic acid production by <em>Lactobacillus</em> inhibits the growth of other bacterial species. Bacterial vaginosis (BV) is characterized by depletion of vaginal <em>Lactobacillus</em> and treatment with current choice antibiotics often fails urging novel alternatives including probiotics or prebiotics. Testing new components for BV treatment often utilize in vitro quantification of <em>Lactobacillus</em>. Thus, this study aimed to compare methods for <em>L. crispatus</em> and <em>L. gasseri</em> quantification. Type strains were cultured in Yeast extract/peptone/tryptone/Tween 80/glucose (LAPTg) and New York City III (NYCIII) broth media, and their glucose-restricted preparations (LAPTgr, NYCIIIgr). Bacterial growth was assessed by measurements of optical density at 540 nm (OD<sub>540</sub>) and plate counting (PC) (CFU/mL) at 0 h, 8 h, 12 h, and 24 h. Measurements of bacterial growth at all timepoints were compared with ANOVA at 5 % significance level. Higher OD<sub>540</sub> reads were observed in LAPTg (<em>p</em> < 0.05) and NYCIII (<em>p</em> < 0.05) with <em>L. crispatus</em> and <em>L. gasseri</em> when compared to LAPTgr and NYCIIIgr, respectively. However, PC did not differ between LAPTg and LAPTgr (<em>p</em> = 0.628 for <em>L. crispatus</em>; <em>p</em> = 0.161 for <em>L. gasseri</em>). In NYCIII, only <em>L. crispatus</em> exhibited higher PC in NYCIII when compared to NYCIIIgr (<em>p</em> = 0.016). These findings suggest that PC does not reflect <em>Lactobacillus</em> spp. counts under the tested conditions. Future studies exploring BV treatments should combine OD measurements with methods for <em>Lactobacillus</em> quantification other than PC, e. g. molecular methods.</div></div>","PeriodicalId":16409,"journal":{"name":"Journal of microbiological methods","volume":"236 ","pages":"Article 107158"},"PeriodicalIF":1.7,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144225702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Madhurie Kumar Seth, K. Srinivas, A. Charan Kumari
{"title":"Classifying fungi biodiversity using hybrid transformer models","authors":"Madhurie Kumar Seth, K. Srinivas, A. Charan Kumari","doi":"10.1016/j.mimet.2025.107155","DOIUrl":"10.1016/j.mimet.2025.107155","url":null,"abstract":"<div><div>Fungi are essential members of ecosystems, playing key roles in nutrient cycling, agriculture, and medicine. Their classification into proper species helps us to understand their biodiversity, allowing us to leverage their ecological and practical benefits. A new hybrid deep learning-based technique has been proposed, merging the Vision Transformer and Swin Transformer models with transfer learning frameworks like MobileNetV2, DenseNet121, and EfficientNetB0 for Fungi multiclass classification. This study utilized a publicly available dataset containing 9115 images of five fungal species from UC Irvine Machine Learning Repository. To address significant class imbalance, several data augmentation techniques were employed. The results showed that the Swin Transformer combined with DenseNet121 achieved the highest classification accuracy of 96.96 % for training, 95.97 % for validation, and 95.57 % for testing, while other models like ViT-DenseNet121 and Swin-MobileNetV2 also delivered competitive results. Using confusion matrices and benchmark classification metrics, and paired statistical testing, the analysis highlights the models' ability to generalize effectively and minimize misclassifications. To further ensure the robustness of the findings, a five-fold cross-validation was performed across all hybrid models. Additionally, explainable AI techniques, specifically Grad-CAM visualizations, were employed to interpret the model's focus areas, confirming attention to biologically significant structures. This research demonstrates a balance between modeling local features and capturing global context. Indeed, these hybrid models prove to be scalable and efficient for complex biological datasets. This interdisciplinary study bridges ecology and advanced technology by applying deep learning to enhance fungal classification. This study aims to improve the management and understanding of fungal biodiversity for the promotion of conservational and sustainable practices for the betterment of our ecosystem. The findings have significant applications, including sustainable agriculture through early detection of fungal plant pathogens, improved medical diagnostics for fungal infections, and biodiversity conservation through precise species monitoring.</div></div>","PeriodicalId":16409,"journal":{"name":"Journal of microbiological methods","volume":"236 ","pages":"Article 107155"},"PeriodicalIF":1.7,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144216116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}